Extend BoxDiff to SDXL (SDXL-based layout-to-image generation)
Improve BoxDiff to Stable Diffusion XL
CUDA_VISIBLE_DEVICES=4 python run_sd_boxdiff.py --prompt "A rabbit wearing sunglasses looks very proud" --P 0.2 --L 1 --seeds [1,2,3,4,5,6,7,8,9] --token_indices [2,4] --bbox [[67,87,366,512],[66,130,364,262]] --sd_xl TrueBoxDiff on SDXL is quite sensitive to the --max_iter_to_alter and weight_loss
I did some simple experiments on above prompt. The results are in output files.
Hi, thank you for your contribution to applying Boxdiff in SDXL. However, I met some bugs when implementing this code.
I see the latent updating code in https://github.com/Cominclip/BoxDiff-XL/blob/bc19e5bae043f00c61c1dc686205e75f84d7ed83/pipeline/sdxl_pipeline_boxdiff.py#L695 is different from that on SD1.4. Originally, Boxdiff calculated the attention map without unconditional branch. However, in your code, it seems add a uncondition text emb but still uses one latent [1,4,128,128]. I afraid this is a bug. So can u tell me how to debug this to achieve corresponding results? Thank u.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.